© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89827
    Prev
    Next
    INDEX
    Explanations

    words related to projects and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echa
    -0.08
    tron
    -0.07
    odont
    -0.07
    AccessException
    -0.07
    etsk
    -0.07
    ooter
    -0.07
    alleries
    -0.07
     Roller
    -0.06
    rent
    -0.06
    ncias
    -0.06
    POSITIVE LOGITS
     lt
    0.06
    åºķ
    0.06
    ÑĮко
    0.06
    ìĬ¤ë¡ľ
    0.05
    thag
    0.05
     Sink
    0.05
    bracht
    0.05
    íĮĶ
    0.05
    istically
    0.05
     Find
    0.05
    Activations Density 0.033%

    No Known Activations